frandovi/vit-base-patch16-224-in21k-euroSat
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2068
- Train Accuracy: 0.9613
- Train Top-3-accuracy: 0.9903
- Validation Loss: 0.2501
- Validation Accuracy: 0.9650
- Validation Top-3-accuracy: 0.9913
- Epoch: 4
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 665, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
---|---|---|---|---|---|---|
1.2723 | 0.6941 | 0.8604 | 0.6544 | 0.8643 | 0.9573 | 0 |
0.4646 | 0.9004 | 0.9707 | 0.4014 | 0.9216 | 0.9784 | 1 |
0.3004 | 0.9348 | 0.9825 | 0.2985 | 0.9446 | 0.9855 | 2 |
0.2351 | 0.9514 | 0.9875 | 0.2611 | 0.9570 | 0.9892 | 3 |
0.2068 | 0.9613 | 0.9903 | 0.2501 | 0.9650 | 0.9913 | 4 |
Framework versions
- Transformers 4.39.1
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 7